slide1 n.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
Simple Linear Regression (SLR) CHE1147 Saed Sayad University of Toronto PowerPoint Presentation
Download Presentation
Simple Linear Regression (SLR) CHE1147 Saed Sayad University of Toronto

Loading in 2 Seconds...

play fullscreen
1 / 69

Simple Linear Regression (SLR) CHE1147 Saed Sayad University of Toronto - PowerPoint PPT Presentation


  • 272 Views
  • Uploaded on

Simple Linear Regression (SLR) CHE1147 Saed Sayad University of Toronto. Types of Correlation. Positive correlation. Negative correlation. No correlation. Simple linear regression describes the linear relationship between a predictor variable, plotted on the x -axis, and a

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Simple Linear Regression (SLR) CHE1147 Saed Sayad University of Toronto' - vitalis


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
slide1

Simple Linear Regression (SLR)

CHE1147

Saed Sayad

University of Toronto

slide2

Types of Correlation

Positive correlation

Negative correlation

No correlation

slide3

Simple linear regression describes the

linear relationship between a predictor

variable, plotted on the x-axis, and a

response variable, plotted on the y-axis

dependent Variable (Y)

Independent Variable (X)

slide4

Y

1.0

X

slide5

Y

1.0

X

slide6

Y

X

slide7

ε

Y

ε

X

slide8

Fitting data to a linear model

intercept

slope

residuals

slide9

How to fit data to a linear model?

The Ordinary Least Square Method (OLS)

slide10

Least Squares Regression

Model line:

Residual (ε) =

Sum of squares of residuals =

  • we must find values of and that minimise
slide15

Variance to be

explained by predictors

(SST)

Y

slide16

X1

Variance explained byX1

(SSR)

Y

Variance NOT

explained byX1

(SSE)

slide18

Regression Statistics

Coefficient of Determination

to judge the adequacy of the regression model

slide19

Regression Statistics

Correlation

measures the strength of the linear association between two variables.

slide20

Regression Statistics

Standard Error for the regression model

slide21

ANOVA

ANOVA to test significance of regression

slide26

Confidence Interval on Regression Coefficients

Confidence Interval for the intercept

slide27

Hypotheses Test the Correlation Coefficient

We would reject the null hypothesis if

slide28

Diagnostic Tests For Regressions

Expected distribution of residuals for a linear model with normal distribution or residuals (errors).

slide29

Diagnostic Tests For Regressions

Residuals for a non-linear fit

slide30

Diagnostic Tests For Regressions

Residuals for a quadratic function or polynomial

slide31

Diagnostic Tests For Regressions

Residuals are not homogeneous (increasing in variance)

slide32

Regression – important points

  • Ensure that the range of values
  • sampled for the predictor variable
  • is large enough to capture the full
  • range to responses by the response
  • variable.
slide33

Y

X

Y

X

slide34

Regression – important points

2. Ensure that the distribution of

predictor values is approximately

uniform within the sampled range.

slide35

Y

X

Y

X

slide36

Assumptions of Regression

1. The linear model correctly describes the functional relationship between X and Y.

slide37

Assumptions of Regression

1. The linear model correctly describes the functional relationship between X and Y.

Y

X

slide38

Assumptions of Regression

2. The X variable is measured without error

Y

X

slide39

Assumptions of Regression

3. For any given value of X, the sampled Y values are independent

4. Residuals (errors) are normally distributed.

5. Variances are constant along the regression line.

slide41

The linear model with a single

predictor variable X can easily

be extended to two or more

predictor variables.

slide42

Common variance explained byX1 and X2

Unique variance explained by X2

X2

X1

Y

Unique variance explained byX1

Variance NOT

explained byX1and X2

slide44

Partial Regression Coefficients

intercept

residuals

Partial Regression Coefficients (slopes):Regression coefficient of X after controlling for (holding all other predictors constant) influence of other variables from both X and Y.

slide45

The matrix algebra of

Ordinary Least Square

Intercept and Slopes:

Predicted Values:

Residuals:

slide46

Regression Statistics

How good is our model?

slide47

Regression Statistics

Coefficient of Determination

to judge the adequacy of the regression model

slide48

Regression Statistics

n = sample size

k = number of independent variables

Adjusted R2 are not biased!

slide49

Regression Statistics

Standard Error for the regression model

slide50

ANOVA

at least one!

ANOVA to test significance of regression

slide58

Diagnostic Tests For Regressions

Expected distribution of residuals for a linear model with normal distribution or residuals (errors).

slide60

Model Selection

Avoiding predictors (Xs)

that do not

contribute significantly

to model prediction

slide61

Model Selection

  • - Forward selection
  • The ‘best’ predictor variables are entered, one by one.

- Backward elimination

  • The ‘worst’ predictor variables are eliminated, one by one.
slide65

Multicolinearity

  • The degree of correlation between Xs.
  • A high degree of multicolinearity produces unacceptable uncertainty (large variance) in regression coefficient estimates (i.e., large sampling variation)
  • Imprecise estimates of slopes and even the signs of the coefficients may be misleading.
  • t-tests which fail to reveal significant factors.
slide67

Multicolinearity

  • If the F-test for significance of regression is significant, but tests on the individual regression coefficients are not, multicolinearity may be present.
  • Variance Inflation Factors (VIFs) are very useful measures of multicolinearity. If any VIF exceed 5, multicolinearity is a problem.
model evaluation
Model Evaluation

Prediction Error Sum of Squares

(leave-one-out)